penfever commited on
Commit
77138a0
·
verified ·
1 Parent(s): 2278bea

Training in progress, step 6200

Browse files
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5e1f4c4fa59f36da7d4a95d5d23997fdd02c3b225cb9d0bf0d812f8df0a2c5d8
3
  size 4902257696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87bbd19b2ccb69af85de2a0cf4ba1914c1db8a0d78b0112bdd446e608beaf7a1
3
  size 4902257696
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0feab729e8b327684f1400c0c09231b0b51900ede29ef912a9b99f561dbbc6a7
3
  size 4915960368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a81ffeed483f542bab9a55860c931e7a1f8ea0932fee684a2d4dd39cf154f2e
3
  size 4915960368
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7e52c46bd0be7d9723677ebebed3ab8ad95a55c19b00b238538f0c6bfd123b7e
3
  size 4983068496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0b037cb5fa7d20f5e27e90f7808267159fc6624b524b2196c32dfcbb46968e7
3
  size 4983068496
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c50978ad80fb792d992da3ccb28825188b883c0787077e8d9c4b82641a4f9c51
3
  size 1580230264
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0720b1e53a639717f69adf8c263a538a84cc23653d848ca3f378af550dfe7cdd
3
  size 1580230264
trainer_log.jsonl CHANGED
@@ -1201,3 +1201,42 @@
1201
  {"current_steps": 6005, "total_steps": 9128, "loss": 0.2158, "lr": 1.2653867852173223e-05, "epoch": 4.605293440736479, "percentage": 65.79, "elapsed_time": "1 day, 13:19:09", "remaining_time": "19:24:30"}
1202
  {"current_steps": 6010, "total_steps": 9128, "loss": 0.2192, "lr": 1.2618312282238451e-05, "epoch": 4.609129267357115, "percentage": 65.84, "elapsed_time": "1 day, 13:20:49", "remaining_time": "19:22:32"}
1203
  {"current_steps": 6015, "total_steps": 9128, "loss": 0.2113, "lr": 1.258278370089113e-05, "epoch": 4.612965093977753, "percentage": 65.9, "elapsed_time": "1 day, 13:22:32", "remaining_time": "19:20:36"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1201
  {"current_steps": 6005, "total_steps": 9128, "loss": 0.2158, "lr": 1.2653867852173223e-05, "epoch": 4.605293440736479, "percentage": 65.79, "elapsed_time": "1 day, 13:19:09", "remaining_time": "19:24:30"}
1202
  {"current_steps": 6010, "total_steps": 9128, "loss": 0.2192, "lr": 1.2618312282238451e-05, "epoch": 4.609129267357115, "percentage": 65.84, "elapsed_time": "1 day, 13:20:49", "remaining_time": "19:22:32"}
1203
  {"current_steps": 6015, "total_steps": 9128, "loss": 0.2113, "lr": 1.258278370089113e-05, "epoch": 4.612965093977753, "percentage": 65.9, "elapsed_time": "1 day, 13:22:32", "remaining_time": "19:20:36"}
1204
+ {"current_steps": 6020, "total_steps": 9128, "loss": 0.2189, "lr": 1.2547282238029213e-05, "epoch": 4.616800920598389, "percentage": 65.95, "elapsed_time": "1 day, 13:24:11", "remaining_time": "19:18:37"}
1205
+ {"current_steps": 6025, "total_steps": 9128, "loss": 0.2273, "lr": 1.2511808023451523e-05, "epoch": 4.6206367472190255, "percentage": 66.01, "elapsed_time": "1 day, 13:25:49", "remaining_time": "19:16:38"}
1206
+ {"current_steps": 6030, "total_steps": 9128, "loss": 0.2214, "lr": 1.2476361186857262e-05, "epoch": 4.624472573839663, "percentage": 66.06, "elapsed_time": "1 day, 13:27:29", "remaining_time": "19:14:40"}
1207
+ {"current_steps": 6035, "total_steps": 9128, "loss": 0.2172, "lr": 1.2440941857845516e-05, "epoch": 4.628308400460299, "percentage": 66.12, "elapsed_time": "1 day, 13:29:14", "remaining_time": "19:12:45"}
1208
+ {"current_steps": 6040, "total_steps": 9128, "loss": 0.2023, "lr": 1.2405550165914806e-05, "epoch": 4.632144227080936, "percentage": 66.17, "elapsed_time": "1 day, 13:30:56", "remaining_time": "19:10:48"}
1209
+ {"current_steps": 6045, "total_steps": 9128, "loss": 0.2103, "lr": 1.2370186240462622e-05, "epoch": 4.635980053701573, "percentage": 66.22, "elapsed_time": "1 day, 13:32:38", "remaining_time": "19:08:51"}
1210
+ {"current_steps": 6050, "total_steps": 9128, "loss": 0.2001, "lr": 1.233485021078491e-05, "epoch": 4.639815880322209, "percentage": 66.28, "elapsed_time": "1 day, 13:34:14", "remaining_time": "19:06:52"}
1211
+ {"current_steps": 6055, "total_steps": 9128, "loss": 0.2164, "lr": 1.2299542206075641e-05, "epoch": 4.643651706942846, "percentage": 66.33, "elapsed_time": "1 day, 13:35:56", "remaining_time": "19:04:55"}
1212
+ {"current_steps": 6060, "total_steps": 9128, "loss": 0.2179, "lr": 1.226426235542633e-05, "epoch": 4.647487533563483, "percentage": 66.39, "elapsed_time": "1 day, 13:37:34", "remaining_time": "19:02:56"}
1213
+ {"current_steps": 6065, "total_steps": 9128, "loss": 0.2032, "lr": 1.2229010787825529e-05, "epoch": 4.6513233601841195, "percentage": 66.44, "elapsed_time": "1 day, 13:39:15", "remaining_time": "19:00:59"}
1214
+ {"current_steps": 6070, "total_steps": 9128, "loss": 0.207, "lr": 1.2193787632158411e-05, "epoch": 4.655159186804756, "percentage": 66.5, "elapsed_time": "1 day, 13:40:52", "remaining_time": "18:59:00"}
1215
+ {"current_steps": 6075, "total_steps": 9128, "loss": 0.2091, "lr": 1.2158593017206263e-05, "epoch": 4.658995013425393, "percentage": 66.55, "elapsed_time": "1 day, 13:42:33", "remaining_time": "18:57:03"}
1216
+ {"current_steps": 6080, "total_steps": 9128, "loss": 0.2079, "lr": 1.2123427071646003e-05, "epoch": 4.66283084004603, "percentage": 66.61, "elapsed_time": "1 day, 13:44:14", "remaining_time": "18:55:06"}
1217
+ {"current_steps": 6085, "total_steps": 9128, "loss": 0.2119, "lr": 1.2088289924049766e-05, "epoch": 4.666666666666667, "percentage": 66.66, "elapsed_time": "1 day, 13:45:52", "remaining_time": "18:53:07"}
1218
+ {"current_steps": 6090, "total_steps": 9128, "loss": 0.2027, "lr": 1.2053181702884353e-05, "epoch": 4.670502493287303, "percentage": 66.72, "elapsed_time": "1 day, 13:47:32", "remaining_time": "18:51:09"}
1219
+ {"current_steps": 6095, "total_steps": 9128, "loss": 0.2101, "lr": 1.2018102536510846e-05, "epoch": 4.67433831990794, "percentage": 66.77, "elapsed_time": "1 day, 13:49:10", "remaining_time": "18:49:11"}
1220
+ {"current_steps": 6100, "total_steps": 9128, "loss": 0.2046, "lr": 1.1983052553184083e-05, "epoch": 4.678174146528577, "percentage": 66.83, "elapsed_time": "1 day, 13:50:54", "remaining_time": "18:47:15"}
1221
+ {"current_steps": 6105, "total_steps": 9128, "loss": 0.2034, "lr": 1.1948031881052187e-05, "epoch": 4.6820099731492135, "percentage": 66.88, "elapsed_time": "1 day, 13:52:30", "remaining_time": "18:45:16"}
1222
+ {"current_steps": 6110, "total_steps": 9128, "loss": 0.2064, "lr": 1.1913040648156144e-05, "epoch": 4.685845799769851, "percentage": 66.94, "elapsed_time": "1 day, 13:54:07", "remaining_time": "18:43:17"}
1223
+ {"current_steps": 6115, "total_steps": 9128, "loss": 0.2162, "lr": 1.1878078982429289e-05, "epoch": 4.689681626390487, "percentage": 66.99, "elapsed_time": "1 day, 13:55:43", "remaining_time": "18:41:18"}
1224
+ {"current_steps": 6120, "total_steps": 9128, "loss": 0.2073, "lr": 1.184314701169685e-05, "epoch": 4.693517453011124, "percentage": 67.05, "elapsed_time": "1 day, 13:57:30", "remaining_time": "18:39:23"}
1225
+ {"current_steps": 6125, "total_steps": 9128, "loss": 0.2063, "lr": 1.1808244863675498e-05, "epoch": 4.697353279631761, "percentage": 67.1, "elapsed_time": "1 day, 13:59:10", "remaining_time": "18:37:26"}
1226
+ {"current_steps": 6130, "total_steps": 9128, "loss": 0.2046, "lr": 1.1773372665972872e-05, "epoch": 4.701189106252397, "percentage": 67.16, "elapsed_time": "1 day, 14:00:54", "remaining_time": "18:35:31"}
1227
+ {"current_steps": 6135, "total_steps": 9128, "loss": 0.2106, "lr": 1.1738530546087086e-05, "epoch": 4.705024932873034, "percentage": 67.21, "elapsed_time": "1 day, 14:02:34", "remaining_time": "18:33:34"}
1228
+ {"current_steps": 6140, "total_steps": 9128, "loss": 0.2057, "lr": 1.17037186314063e-05, "epoch": 4.708860759493671, "percentage": 67.27, "elapsed_time": "1 day, 14:04:10", "remaining_time": "18:31:34"}
1229
+ {"current_steps": 6145, "total_steps": 9128, "loss": 0.2039, "lr": 1.1668937049208251e-05, "epoch": 4.7126965861143075, "percentage": 67.32, "elapsed_time": "1 day, 14:05:53", "remaining_time": "18:29:39"}
1230
+ {"current_steps": 6150, "total_steps": 9128, "loss": 0.2068, "lr": 1.1634185926659733e-05, "epoch": 4.716532412734944, "percentage": 67.38, "elapsed_time": "1 day, 14:07:33", "remaining_time": "18:27:41"}
1231
+ {"current_steps": 6155, "total_steps": 9128, "loss": 0.2019, "lr": 1.1599465390816232e-05, "epoch": 4.720368239355581, "percentage": 67.43, "elapsed_time": "1 day, 14:09:17", "remaining_time": "18:25:46"}
1232
+ {"current_steps": 6160, "total_steps": 9128, "loss": 0.2021, "lr": 1.1564775568621367e-05, "epoch": 4.724204065976218, "percentage": 67.48, "elapsed_time": "1 day, 14:10:53", "remaining_time": "18:23:47"}
1233
+ {"current_steps": 6165, "total_steps": 9128, "loss": 0.2044, "lr": 1.1530116586906456e-05, "epoch": 4.728039892596855, "percentage": 67.54, "elapsed_time": "1 day, 14:12:36", "remaining_time": "18:21:51"}
1234
+ {"current_steps": 6170, "total_steps": 9128, "loss": 0.2044, "lr": 1.1495488572390106e-05, "epoch": 4.731875719217491, "percentage": 67.59, "elapsed_time": "1 day, 14:14:16", "remaining_time": "18:19:54"}
1235
+ {"current_steps": 6175, "total_steps": 9128, "loss": 0.2154, "lr": 1.1460891651677637e-05, "epoch": 4.735711545838128, "percentage": 67.65, "elapsed_time": "1 day, 14:15:54", "remaining_time": "18:17:56"}
1236
+ {"current_steps": 6180, "total_steps": 9128, "loss": 0.206, "lr": 1.1426325951260746e-05, "epoch": 4.739547372458765, "percentage": 67.7, "elapsed_time": "1 day, 14:17:34", "remaining_time": "18:15:59"}
1237
+ {"current_steps": 6185, "total_steps": 9128, "loss": 0.2079, "lr": 1.1391791597516964e-05, "epoch": 4.7433831990794015, "percentage": 67.76, "elapsed_time": "1 day, 14:19:19", "remaining_time": "18:14:05"}
1238
+ {"current_steps": 6190, "total_steps": 9128, "loss": 0.209, "lr": 1.1357288716709174e-05, "epoch": 4.747219025700039, "percentage": 67.81, "elapsed_time": "1 day, 14:20:54", "remaining_time": "18:12:05"}
1239
+ {"current_steps": 6195, "total_steps": 9128, "loss": 0.2047, "lr": 1.1322817434985257e-05, "epoch": 4.751054852320675, "percentage": 67.87, "elapsed_time": "1 day, 14:22:37", "remaining_time": "18:10:10"}
1240
+ {"current_steps": 6200, "total_steps": 9128, "loss": 0.2022, "lr": 1.1288377878377514e-05, "epoch": 4.754890678941312, "percentage": 67.92, "elapsed_time": "1 day, 14:24:18", "remaining_time": "18:08:13"}
1241
+ {"current_steps": 6205, "total_steps": 9128, "loss": 0.2003, "lr": 1.1253970172802276e-05, "epoch": 4.758726505561949, "percentage": 67.98, "elapsed_time": "1 day, 14:27:11", "remaining_time": "18:06:51"}
1242
+ {"current_steps": 6210, "total_steps": 9128, "loss": 0.1865, "lr": 1.121959444405941e-05, "epoch": 4.762562332182585, "percentage": 68.03, "elapsed_time": "1 day, 14:28:52", "remaining_time": "18:04:54"}